|
|
Bohnett, E., Faryabi, S. P., Lewison, R., An, L., Bian, X., Rajabi, A. M., Jahed, N., Rooyesh, H., Mills, E., Ramos, S., Mesnildrey, N., Perez, C. M. S., Taylor, J., Terentyev, V., Ostrowski, S. (2023). Human expertise combined with artificial intelligence improves performance of snow leopard camera trap studies. Global Ecology & Conservation, 41(e02350), 1–13.
Abstract: Camera trapping is the most widely used data collection method for estimating snow leopard (Panthera uncia) abundance; however, the accuracy of this method is limited by human observer errors from misclassifying individuals in camera trap images. We evaluated the extent Whiskerbook (www.whiskerbook.org), an artificial intelligence (AI) software, could reduce this error rate and enhance the accuracy of capture-recapture abundance estimates. Using 439 images of 34 captive snow leopard individuals, classification was performed by five observers with prior experience in individual snow leopard ID (“experts”) and five observers with no such experience (“novices”). The “expert” observers classified 35 out of 34 snow leopard individuals, on average erroneously splitting one individual into two, thus resulting in a higher number than true individuals. The success rate of experts was 90 %, with less than a 3 % error in estimating the population size in capture-recapture modeling. However, the “novice” observers successfully matched 71 % of encounters, recognizing 25 out of 34 individuals, underestimating the population by 25 %. It was found that expert observers significantly outperformed novice observers, making statistically fewer errors (Mann Whitney U test P = 0.01) and finding the true number of individuals (P = 0.01). These differences were contrasted with a previous study by Johansson et al. 2020, using the same subset of 16 individuals from European zoos. With the help of AI and the Whiskerbook platform, “experts” were able to match 87 % of encounters and identify 15 out of 16 individuals, with modeled estimates of 16 ± 1 individuals. In contrast, “novices” were 63 % accurate in matching encounters and identified 12 out of 16 individuals, modeling 12 ± 1 individuals that underestimated the population size by 12 %. When comparing the performance of observers using AI and the Whiskerbook platform to observers performing the tasks manually, we found that observers using Whiskerbook made significantly fewer errors in splitting one individual into two (P = 0.04). However, there were also a significantly higher number of combination errors, where two individuals were combined into one (P = 0.01). Specifically, combination errors were found to be made by “novices” (P = 0.04). Although AI benefited both expert and novice observers, expert observers outperformed novices. Our results suggest that AI effectively reduced the misclassification of individual snow leopards in camera trap studies, improving abundance estimates. However, even with AI support, expert observers were needed to obtain the most accurate estimates.
|
|
|
|
Allen, M. L., Rovero, F., Oberosler, V., Augugliaro, C., Krofel, M. (2023). Effects of snow leopards (Panthera uncia) on olfactory communication of Pallas’s cats (Otocolobus manul) in the Altai Mountains, Mongolia. Behaviour, , 1–9.
Abstract: Olfactory communication is important for many solitary carnivores to delineate territories and communicate with potential mates and competitors. Pallas’s cats (Otocolobus manul) are small felids with little published research on their ecology and behaviour, including if they avoid or change behaviours due to dominant carnivores. We studied their olfactory communication and visitation at scent-marking sites using camera traps in two study areas in Mongolia. We documented four types of olfactory communication behaviours, and olfaction (sniffing) was the most frequent. Pallas’s cats used olfactory communication most frequently at sites that were not visited by snow leopards (Panthera uncia) and when they used communal scent-marking sites, they were more likely to use olfactory communication when a longer time had elapsed since the last visit by a snow leopard. This suggests that Pallas’s cats may reduce advertising their presence in response to occurrence of snow leopards, possibly to limit predation risk.
|
|
|
|
Zhang, C., Ma, T., Ma, D. (2023). Status of the snow leopard Panthera uncia in the Qilian Mountains, Gansu Province, China. Oryx, , 1–6.
Abstract: Population density estimation is integral to the effective conservation and management of wildlife. The snow leopard Panthera uncia is categorized as Vulnerable on the IUCN Red List, and reliable information on its density is a prerequisite for its conservation and management. Little is known about the status of the snow leopard in the central and eastern Qilian Mountains, China. To address this, we estimated the population density of the snow leopard using a spatially explicit capture–recapture model based on camera trapping in Machang in the central and eastern Qilian Mountains during January–March 2019. We set up
40 camera traps and recorded 84 separate snow leopard captures over 3,024 trap-days. We identified 18 individual snow leopards and estimated their density to be 2.26/100 km. Our study provides baseline information on the snow leopard and the first population estimate for the species in the central and eastern Qilian Mountains.
|
|
|
|
Sanyal, O., Bashir, T., Rana, M., Chandan, P. (2023). First photographic record of the snow leopard Panthera uncia in Kishtwar High Altitude National Park, Jammu and Kashmir, India. Oryx, , 1–5.
Abstract: The snow leopard Panthera uncia is categorized as Vulnerable on the IUCN Red List. It is the least well-known of the large felids because of its shy and elusive nature and the inaccessible terrain it inhabits across the mountains of Central and South Asia. We report the first photographic record of the snow leopard in Kishtwar High Altitude National Park, India. During our camera-trapping surveys, conducted using a grid-based design, we obtained eight photographs of snow leopards, the first at 3,280 m altitude on 19 September 2022 and subsequent photographs over 3,004-3,878 m altitude. We identified at least four different individuals, establishing the species’ occurrence in Kiyar, Nanth and Renai catchments, with a capture rate of 0.123 ± SE 0.072 captures/100 trap-nights. ghts. We also recorded the presence of snow leopard prey species, including the Siberian ibex Capra sibirica, Himalayan musk deer Moschus leucogaster, long-tailed marmot Marmota caudata and pika Ochotona sp., identifying the area as potential snow leopard habitat. Given the location of Kishtwar High Altitude National Park, this record is significant for the overall snow leopard conservation landscape in India. We recommend a comprehensive study across the Kishtwar landscape to assess the occupancy, abundance, demography and movement patterns of the snow leopard and its prey. In addition, interactions between the snow leopard and pastoral communities should be assessed to understand the challenges facing the conservation and management of this important high-altitude region.
|
|
